Fourier ptychography: current applications and future promises

PC Konda, L Loetgering, KC Zhou, S Xu, AR Harvey… - Optics express, 2020 - opg.optica.org
Traditional imaging systems exhibit a well-known trade-off between the resolution and the
field of view of their captured images. Typical cameras and microscopes can either “zoom in” …

Compressed sensing-based robust phase retrieval via deep generative priors

F Shamshad, A Ahmed - IEEE Sensors Journal, 2020 - ieeexplore.ieee.org
Algorithmic phase retrieval offers an alternative means to recover the phase of optical
images without requiring sophisticated measurement setups such as holography. This …

Complex-valued retrievals from noisy images using diffusion models

N Torem, R Ronen, YY Schechner… - Proceedings of the …, 2023 - openaccess.thecvf.com
In diverse microscopy modalities, sensors measure only real-valued intensities. Additionally,
the sensor readouts are affected by Poissonian-distributed photon noise. Traditional …

Dynamic Fourier ptychography with deep spatiotemporal priors

P Bohra, T Pham, Y Long, J Yoo, M Unser - Inverse Problems, 2023 - iopscience.iop.org
Fourier ptychography (FP) involves the acquisition of several low-resolution intensity images
of a sample under varying illumination angles. They are then combined into a high …

Makeup-Guided Facial Privacy Protection via Untrained Neural Network Priors

F Shamshad, M Naseer, K Nandakumar - arxiv preprint arxiv:2408.12387, 2024 - arxiv.org
Deep learning-based face recognition (FR) systems pose significant privacy risks by tracking
users without their consent. While adversarial attacks can protect privacy, they often produce …

Sound field reconstruction in rooms with deep generative models

X Karakonstantis… - INTER-NOISE and …, 2021 - ingentaconnect.com
The characterization of Room Impulse Responses (RIR) over an extended region in a room
by means of measurements requires dense spatial with many microphones. This can often …

Deep S3PR: Simultaneous Source Separation and Phase Retrieval Using Deep Generative Models

CA Metzler, G Wetzstein - ICASSP 2021-2021 IEEE …, 2021 - ieeexplore.ieee.org
This paper introduces and solves the simultaneous source separation and phase retrieval (S
3 PR) problem. S 3 PR is an important but largely unsolved problem in a number application …

Subsampled fourier ptychography using pretrained invertible and untrained network priors

F Shamshad, A Hanif, A Ahmed - arxiv preprint arxiv:2005.07026, 2020 - arxiv.org
Recently pretrained generative models have shown promising results for subsampled
Fourier Ptychography (FP) in terms of quality of reconstruction for extremely low sampling …

Statistical Inference for Inverse Problems: From Sparsity-Based Methods to Neural Networks

PN Bohra - 2024 - infoscience.epfl.ch
In inverse problems, the task is to reconstruct an unknown signal from its possibly noise-
corrupted measurements. Penalized-likelihood-based estimation and Bayesian estimation …

Class-specific blind deconvolutional phase retrieval under a generative prior

F Shamshad, A Ahmed - arxiv preprint arxiv:2002.12578, 2020 - arxiv.org
In this paper, we consider the highly ill-posed problem of jointly recovering two real-valued
signals from the phaseless measurements of their circular convolution. The problem arises …